Segmentation-Driven 6D Object Pose Estimation

The most recent trend in estimating the 6D pose of rigid objects has been to train deep networks to either directly regress the pose from the image or to predict the 2D locations of 3D keypoints, from which the pose can be obtained using a PnP algorithm. In both cases, the object is treated as a glo...

Full description

Saved in:
Bibliographic Details
Main Authors: Hu, Yinlin, Hugonot, Joachim, Fua, Pascal, Salzmann, Mathieu
Format: Conference Proceeding
Language:English
Subjects:
3D from Single Image
Accuracy
Categorization
Computer architecture
Computer vision
Deep Learning
Recognition: Detection
Pattern recognition
Pose estimation
Prediction algorithms
Real-time systems
Reliability
Retrieval
Three-dimensional displays
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!